Ghent University Academic Bibliography

Advanced

A bayesian model for exploiting application constraints to enable unsupervised training of a P300 based BCI

Pieter-Jan Kindermans, David Verstraeten UGent and Benjamin Schrauwen (2012) PLOS ONE. 7(4).
abstract
This work introduces a novel classifier for a P300-based speller, which, contrary to common methods, can be trained entirely unsupervisedly using an Expectation Maximization approach, eliminating the need for costly dataset collection or tedious calibration sessions. We use publicly available datasets for validation of our method and show that our unsupervised classifier performs competitively with supervised state-of-the-art spellers. Finally, we demonstrate the added value of our method in different experimental settings which reflect realistic usage situations of increasing difficulty and which would be difficult or impossible to tackle with existing supervised or adaptive methods.
Please use this url to cite or link to this publication:
author
organization
year
type
journalArticle (original)
publication status
published
subject
keyword
P300 WAVE, ALGORITHM, COMMUNICATION, COMPETITION 2003, MENTAL PROSTHESIS, BRAIN-COMPUTER-INTERFACE
journal title
PLOS ONE
PLoS One
volume
7
issue
4
article number
e33758
pages
21 pages
Web of Science type
Article
Web of Science id
000304855200022
JCR category
MULTIDISCIPLINARY SCIENCES
JCR impact factor
3.73 (2012)
JCR rank
7/56 (2012)
JCR quartile
1 (2012)
ISSN
1932-6203
DOI
10.1371/journal.pone.0033758
language
English
UGent publication?
yes
classification
A1
copyright statement
I have retained and own the full copyright for this publication
id
2046642
handle
http://hdl.handle.net/1854/LU-2046642
date created
2012-02-27 11:42:38
date last changed
2016-12-21 15:41:58
@article{2046642,
  abstract     = {This work introduces a novel classifier for a P300-based speller, which, contrary to common methods, can be trained entirely unsupervisedly using an Expectation Maximization approach, eliminating the need for costly dataset collection or tedious calibration sessions. We use publicly available datasets for validation of our method and show that our unsupervised classifier performs competitively with supervised state-of-the-art spellers. Finally, we demonstrate the added value of our method in different experimental settings which reflect realistic usage situations of increasing difficulty and which would be difficult or impossible to tackle with existing supervised or adaptive methods.},
  articleno    = {e33758},
  author       = {Kindermans, Pieter-Jan and Verstraeten, David and Schrauwen, Benjamin},
  issn         = {1932-6203},
  journal      = {PLOS ONE},
  keyword      = {P300 WAVE,ALGORITHM,COMMUNICATION,COMPETITION 2003,MENTAL PROSTHESIS,BRAIN-COMPUTER-INTERFACE},
  language     = {eng},
  number       = {4},
  pages        = {21},
  title        = {A bayesian model for exploiting application constraints to enable unsupervised training of a P300 based BCI},
  url          = {http://dx.doi.org/10.1371/journal.pone.0033758},
  volume       = {7},
  year         = {2012},
}

Chicago
Kindermans, Pieter-Jan, David Verstraeten, and Benjamin Schrauwen. 2012. “A Bayesian Model for Exploiting Application Constraints to Enable Unsupervised Training of a P300 Based BCI.” Plos One 7 (4).
APA
Kindermans, P.-J., Verstraeten, D., & Schrauwen, B. (2012). A bayesian model for exploiting application constraints to enable unsupervised training of a P300 based BCI. PLOS ONE, 7(4).
Vancouver
1.
Kindermans P-J, Verstraeten D, Schrauwen B. A bayesian model for exploiting application constraints to enable unsupervised training of a P300 based BCI. PLOS ONE. 2012;7(4).
MLA
Kindermans, Pieter-Jan, David Verstraeten, and Benjamin Schrauwen. “A Bayesian Model for Exploiting Application Constraints to Enable Unsupervised Training of a P300 Based BCI.” PLOS ONE 7.4 (2012): n. pag. Print.